P07.01: Artificial intelligence (AI) weights the importance of clinical and sonographic factors predicting malignancy in unilocular‐solid cysts before surgery (original) (raw)

2019, Ultrasound in Obstetrics & Gynecology

Doppler assessment during their routine 20 weeks anomaly scan. UtA Doppler was considered abnormal if sum of pulsatility index (PI) of both uterine arteries was ≥ 2.5. Women were assigned to 4 risk group categories according with presence of SGA maternal risk factors and UtA results: A. low risk: no risk factors and normal UtA; B. intermediate-low risk: no risk factors and abnormal UtA; C. intermediate-high risk: risk factors present and normal UtA; D. high risk: risk factors present and abnormal UtA. The primary outcome was SGA, defined as a baby with birth weight < 10 th centile according with INTERGROWTH-21st standards. Sensitivity and specificity were calculated. Results: UtA Doppler assessment and birth weight were available in 864 women. Amongst those women, neonatal SGA occurred in 51 (5.90%), UtA was abnormal in 91% of all cases. The overall sensitivity, specificity, positive and negative predictive value were, 33, 88, 16, and 95%, respectively. In the low and intermediate-low risk group sensitivity and negative predictive value were similar to the all population (33, and 96%, respectively) (group A and B). SGA rate detection in the intermediate-low risk group doubled (from 8 to 16 cases). In the intermediate-high and high risk groups (C, D), sensitivity was higher (58%); with a lower negative predictive value (91%). Conclusions: UtA Doppler assessment in the second trimester, as a part of a multiparamenter test for screening for SGA, improves detection rate, especially in the subgroup of patients with risk factors for SGA. Negative predictive value in low-risk women can justify its use routinely.